Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only disclose a generic non-readonly, non-destructive profile, which is the minimum bar here. The description adds nothing about the prepare semantics: whether it creates a pending approval, whether it is reversible, what the preparation returns, or that the actual budget change only lands on confirm. For a mutation-prepare tool this is a meaningful gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence that is front-loaded and free of waste. It is not verbose, but it is under-specified rather than genuinely concise, and the brevity costs it the ability to explain the workflow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters at 20% schema coverage and no output schema, the description carries the burden of explaining the prepare/confirm flow and the amount_micros/items semantics — and does none of it. An agent could call this tool without knowing a confirm step is required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 20% — only customer_id is documented. The description implies campaign_id and amount_micros but never explains that amounts are in micros, that an items array supports batching up to 10 budgets, or how the array form relates to the single campaign_id/amount_micros form. It leaves the poorly documented parameters unclarified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a resource (campaign daily budget) and the workflow action (prepare/update), so the agent knows the target area. However, "Prepare updating" is vague about what preparation actually produces — a pending mutation, a token, an approval request — and it does not distinguish this tool from its direct sibling google_ads_budget_update_confirm or from google_ads_shared_budget_update_prepare.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance is given. Most critically, the description never states that this is the first step of a two-phase flow that must be followed by google_ads_budget_update_confirm, even though that sibling exists. The agent must infer the workflow from the naming convention alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.